Mobile edge computing (MEC) is a promising paradigm for real-time applications with intensive computational needs (e.g., autonomous driving), as it can reduce the processing delay. In this work, we focus on the timeliness of computational-intensive updates, measured by Age-of-Information (AoI), and study how to jointly optimize the task updating and offloading policies for AoI with fractional form. Specifically, we consider edge load dynamics and formulate a task scheduling problem to minimize the expected time-average AoI. The uncertain edge load dynamics, the nature of the fractional objective, and hybrid continuous-discrete action space (due to the joint optimization) make this problem challenging and existing approaches not directly applicable. To this end, we propose a fractional reinforcement learning (RL) framework and prove its convergence. We further design a model-free fractional deep RL (DRL) algorithm, where each device makes scheduling decisions with the hybrid action space without knowing the system dynamics and decisions of other devices. Experimental results show that our proposed algorithms reduce the average AoI by up to 57.6% compared with several non-fractional benchmarks.
论文检索
输入标题、作者或关键词，从 1,248 篇学术成果中精准定位
Object rearrangement in a multi-room setup should produce a reasonable plan that reduces the agent's overall travel and the number of steps. Recent state-of-the-art methods fail to produce such plans because they rely on explicit exploration for discovering unseen objects due to partial observability and a heuristic planner to sequence the actions for rearrangement. This paper proposes a novel task planner to efficiently plan a sequence of actions to discover unseen objects and rearrange misplaced objects within an untidy house to achieve a desired tidy state. The proposed method introduces several innovative techniques, including (i) a method for discovering unseen objects using commonsense knowledge from large language models, (ii) a collision resolution and buffer prediction method based on Cross-Entropy Method to handle blocked goal and swap cases, (iii) a directed spatial graph-based state space for scalability, and (iv) deep reinforcement learning (RL) for producing an efficient plan to simultaneously discover unseen objects and rearrange the visible misplaced ones to minimize the overall traversal. The paper also presents new metrics and a benchmark dataset called MoPOR to evaluate the effectiveness of the rearrangement planning in a multi-room setting. The experimental results demonstrate that the proposed method effectively addresses the multi-room rearrangement problem.
Hardware image signal processing (ISP), aiming at converting RAW inputs to RGB images, consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP parameters are manually tuned in isolation by imaging experts according to application-specific quality and performance metrics, which is time-consuming and biased towards human perception due to complex interaction with the output image. Since the relationship between any single parameter’s variation and the output performance metric is a complex, non-linear function, optimizing such a large number of ISP parameters is challenging. To address this challenge, we propose a novel Sequential ISP parameter optimization model, called the RL-SeqISP model, which utilizes deep reinforcement learning to jointly optimize all ISP parameters for a variety of imaging applications. Concretely, inspired by the sequential tuning process of human experts, the proposed model can progressively enhance image quality by seamlessly integrating information from both the image feature space and the parameter space. Furthermore, a dynamic parameter optimization module is introduced to avoid ISP parameters getting stuck into local optima, which is able to more effectively guarantee the optimal parameters resulting from the sequential learning strategy. These merits of the RL-SeqISP model as well as its high efficiency are substantiated by comprehensive experiments on a wide range of downstream tasks, including two visual analysis tasks (instance segmentation and object detection), and image quality assessment (IQA), as compared with representative methods both quantitatively and qualitatively. In particular, even using only 10% of the training data, our model outperforms other SOTA methods by an average of 7% mAP on two visual analysis tasks.
Reinforcement Learning · Everything Else
Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied to robotics, autonomous driving, and autoregressive text generation. The simplest approach to IL, behavior cloning (BC) is thought to incur sample complexity with unfavorable quadratic dependence on the problem horizon, motivating a variety of different online algorithms that attain improved linear horizon dependence under stronger assumptions on the data and the learner’s access to the expert. We revisit the apparent gap between offline and online IL from a learning-theoretic perspective, with a focus on general policy classes up to and including deep neural networks. Through a new analysis of BC with the logarithmic loss, we show that it is possible to achieve horizon-independent sample complexity in offline IL whenever (i) the range of the cumulative payoffs is controlled, and (ii) an appropriate notion of supervised learning complexity for the policy class is controlled. Specializing our results to deterministic, stationary policies, we show that the gap between offline and online IL is not fundamental: (i) it is possible to achieve linear dependence on horizon in offline IL under dense rewards (matching what was previously only known to be achievable in online IL); and (ii) without further assumptions on the policy class, online IL cannot improve over offline IL with the logarithmic loss, even in benign MDPs. We complement our theoretical results with experiments on standard RL tasks and autoregressive language generation to validate the practical relevance of our findings.
Reinforcement Learning · Deep RL
The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints.However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality.To overcome the difficulties posed by the nonlinearity, we propose a spectral risk measure-constrained RL algorithm, spectral-risk-constrained policy optimization (SRCPO), a bilevel optimization approach that utilizes the duality of spectral risk measures.In the bilevel optimization structure, the outer problem involves optimizing dual variables derived from the risk measures, while the inner problem involves finding an optimal policy given these dual variables.The proposed method, to the best of our knowledge, is the first to guarantee convergence to an optimum in the tabular setting.Furthermore, the proposed method has been evaluated on continuous control tasks and showed the best performance among other RCRL algorithms satisfying the constraints.Our code is available at https://github.com/rllab-snu/Spectral-Risk-Constrained-RL.
Trustworthy Machine Learning
In many Deep Reinforcement Learning (RL) problems, decisions in a trained policy vary in significance for the expected safety and performance of the policy. Since RL policies are very complex, testing efforts should concentrate on states in which the agent's decisions have the highest impact on the expected outcome. In this paper, we propose a novel model-based method to rigorously compute a ranking of state importance across the entire state space. We then focus our testing efforts on the highest-ranked states. In this paper, we focus on testing for safety. However, the proposed methods can be easily adapted to test for performance. In each iteration, our testing framework computes optimistic and pessimistic safety estimates. These estimates provide lower and upper bounds on the expected outcomes of the policy execution across all modeled states in the state space. Our approach divides the state space into safe and unsafe regions upon convergence, providing clear insights into the policy's weaknesses. Two important properties characterize our approach. (1) Optimal Test-Case Selection: At any time in the testing process, our approach evaluates the policy in the states that are most critical for safety. (2) Guaranteed Safety: Our approach can provide formal verification guarantees over the entire state space by sampling only a fraction of the policy. Any safety properties assured by the pessimistic estimate are formally proven to hold for the policy. We provide a detailed evaluation of our framework on several examples, showing that our method discovers unsafe policy behavior with low testing effort.
Reinforcement Learning · Deep RL
Although recent advancements in large language models (LLMs) have significantly improved their performance on various tasks, they still face challenges with complex and symbolic multi-step reasoning, particularly in mathematical reasoning. To bolster the mathematical reasoning capabilities of LLMs, most existing efforts concentrate on seeking assistance from either domain experts or GPT-4 for high-quality process-supervised data, which is not only expensive but also labor-intensive. In our study, we propose an innovative framework, AlphaMath, that bypasses the need for process annotations (from humans or GPTs) by leveraging Monte Carlo Tree Search (MCTS). This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning. Specifically, we integrate a value model with the LLM, automatically generating both process supervision and step-level evaluation signals in MCTS. Furthermore, we propose an efficient inference strategy—step-level beam search, where the value model is crafted to assist the policy model (i.e., LLM) in navigating more effective reasoning paths, rather than solely relying on prior probabilities. The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.
Reinforcement Learning · Deep RL
Allocation tasks represent a class of problems where a limited amount of resources must be allocated to a set of entities at each time step. Prominent examples of this task include portfolio optimization or distributing computational workloads across servers.Allocation tasks are typically bound by linear constraints describing practical requirements that have to be strictly fulfilled at all times. In portfolio optimization, for example, investors may be obligated to allocate less than 30\% of the funds into a certain industrial sector in any investment period. Such constraints restrict the action space of allowed allocations in intricate ways, which makes learning a policy that avoids constraint violations difficult.In this paper, we propose a new method for constrained allocation tasks based on an autoregressive process to sequentially sample allocations for each entity. In addition, we introduce a novel de-biasing mechanism to counter the initial bias caused by sequential sampling. We demonstrate the superior performance of our approach compared to a variety of Constrained Reinforcement Learning (CRL) methods on three distinct constrained allocation tasks: portfolio optimization, computational workload distribution, and a synthetic allocation benchmark. Our code is available at: https://github.com/niklasdbs/paspo
Reinforcement Learning · Deep RL
Deep reinforcement learning (RL) is a powerful approach to complex decision-making. However, one issue that limits its practical application is its brittleness, sometimes failing to train in the presence of small changes in the environment. Motivated by the success of zero-shot transfer—where pre-trained models perform well on related tasks—we consider the problem of selecting a good set of training tasks to maximize generalization performance across a range of tasks. Given the high cost of training, it is critical to select training tasks strategically, but not well understood how to do so. We hence introduce Model-Based Transfer Learning (MBTL), which layers on top of existing RL methods to effectively solve contextual RL problems. MBTL models the generalization performance in two parts: 1) the performance set point, modeled using Gaussian processes, and 2) performance loss (generalization gap), modeled as a linear function of contextual similarity. MBTL combines these two pieces of information within a Bayesian optimization (BO) framework to strategically select training tasks. We show theoretically that the method exhibits sublinear regret in the number of training tasks and discuss conditions to further tighten regret bounds. We experimentally validate our methods using urban traffic and standard continuous control benchmarks. The experimental results suggest that MBTL can achieve up to 43x improved sample efficiency compared with canonical independent training and multi-task training. Further experiments demonstrate the efficacy of BO and the insensitivity to the underlying RL algorithm and hyperparameters. This work lays the foundations for investigating explicit modeling of generalization, thereby enabling principled yet effective methods for contextual RL. Code is available at https://github.com/jhoon-cho/MBTL/.
Reinforcement Learning · Batch Offline
As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, context-based OMRL (COMRL) as a popular paradigm, aims to learn a universal policy conditioned on effective task representations. In this work, by examining several key milestones in the field of COMRL, we propose to integrate these seemingly independent methodologies into a unified framework. Most importantly, we show that the pre-existing COMRL algorithms are essentially optimizing the same mutual information objective between the task variable $M$ and its latent representation $Z$ by implementing various approximate bounds. Such theoretical insight offers ample design freedom for novel algorithms. As demonstrations, we propose a supervised and a self-supervised implementation of $I(Z; M)$, and empirically show that the corresponding optimization algorithms exhibit remarkable generalization across a broad spectrum of RL benchmarks, context shift scenarios, data qualities and deep learning architectures. This work lays the information theoretic foundation for COMRL methods, leading to a better understanding of task representation learning in the context of reinforcement learning. Given itsgenerality, we envision our framework as a promising offline pre-training paradigm of foundation models for decision making.
Reinforcement Learning · Deep RL
Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to---or knowledge of---an underlying, unobservable state space. Our metric, the λ-discrepancy, is the difference between two distinct temporal difference (TD) value estimates, each computed using TD(λ) with a different value of λ. Since TD(λ=0) makes an implicit Markov assumption and TD(λ=1) does not, a discrepancy between these estimates is a potential indicator of a non-Markovian state representation. Indeed, we prove that the λ-discrepancy is exactly zero for all Markov decision processes and almost always non-zero for a broad class of partially observable environments. We also demonstrate empirically that, once detected, minimizing the λ-discrepancy can help with learning a memory function to mitigate the corresponding partial observability. We then train a reinforcement learning agent that simultaneously constructs two recurrent value networks with different λ parameters and minimizes the difference between them as an auxiliary loss. The approach scales to challenging partially observable domains, where the resulting agent frequently performs significantly better (and never performs worse) than a baseline recurrent agent with only a single value network.
Reinforcement Learning · Deep RL
While the conditional sequence modeling with the transformer architecture has demonstrated its effectiveness in dealing with offline reinforcement learning (RL) tasks, it is struggle to handle out-of-distribution states and actions.Existing work attempts to address this issue by data augmentation with the learned policy or adding extra constraints with the value-based RL algorithm. However, these studies still fail to overcome the following challenges: (1) insufficiently utilizing the historical temporal information among inter-steps, (2) overlooking the local intra-step relationships among return-to-gos (RTGs), states, and actions, (3) overfitting suboptimal trajectories with noisy labels. To address these challenges, we propose $\textbf{D}$ecision $\textbf{M}$amba ($\textbf{DM}$), a novel multi-grained state space model (SSM) with a self-evolving policy learning strategy.DM explicitly models the historical hidden state to extract the temporal information by using the mamba architecture. To capture the relationship among RTG-state-action triplets, a fine-grained SSM module is designed and integrated into the original coarse-grained SSM in mamba, resulting in a novel mamba architecture tailored for offline RL. Finally, to mitigate the overfitting issue on noisy trajectories, a self-evolving policy is proposed by using progressive regularization. The policy evolves by using its own past knowledge to refine the suboptimal actions, thus enhancing its robustness on noisy demonstrations. Extensive experiments on various tasks show that DM outperforms other baselines substantially.
Reinforcement Learning · Deep RL
The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain.Meta-reinforcement learning (meta-RL) approaches abandon the aim of zero-shot *generalization*—the goal of standard reinforcement learning (RL)—in favor of few-shot *adaptation*, and thus hold promise for bridging larger generalization gaps.While learning this meta-level adaptive behavior still requires substantial data, efficient environment simulators approaching real-world complexity are growing in prevalence.Even so, hand-designing sufficiently diverse and numerous simulated training tasks for these complex domains is prohibitively labor-intensive.Domain randomization (DR) and procedural generation (PG), offered as solutions to this problem, require simulators to possess carefully-defined parameters which directly translate to meaningful task diversity—a similarly prohibitive assumption.In this work, we present **DIVA**, an evolutionary approach for generating diverse training tasks in such complex, open-ended simulators.Like unsupervised environment design (UED) methods, DIVA can be applied to arbitrary parameterizations, but can additionally incorporate realistically-available domain knowledge—thus inheriting the *flexibility* and *generality* of UED, and the supervised *structure* embedded in well-designed simulators exploited by DR and PG.Our empirical results showcase DIVA's unique ability to overcome complex parameterizations and successfully train adaptive agent behavior, far outperforming competitive baselines from prior literature.These findings highlight the potential of such *semi-supervised environment design* (SSED) approaches, of which DIVA is the first humble constituent, to enable training in realistic simulated domains, and produce more robust and capable adaptive agents.Our code is available at [https://github.com/robbycostales/diva](https://github.com/robbycostales/diva).
Reinforcement Learning · Deep RL
Reinforcement learning from human feedback (RLHF) provides a principled framework for aligning AI systems with human preference data. For various reasons, e.g., personal bias, context ambiguity, lack of training, etc, human annotators may give incorrect or inconsistent preference labels. To tackle this challenge, we propose a robust RLHF approach -- $R^3M$, which models the potentially corrupted preference label as sparse outliers. Accordingly, we formulate the robust reward learning as an $\ell_1$-regularized maximum likelihood estimation problem. Computationally, we develop an efficient alternating optimization algorithm, which only incurs negligible computational overhead compared with the standard RLHF approach. Theoretically, we prove that under proper regularity conditions, $R^3M$ can consistently learn the underlying reward and identify outliers, provided that the number of outlier labels scales sublinearly with the preference sample size. Furthermore, we remark that $R^3M$ is versatile and can be extended to various preference optimization methods, including direct preference optimization (DPO). Our experiments on robotic control and natural language generation with large language models (LLMs) show that $R^3M$ improves robustness of the reward against several types of perturbations to the preference data.
Reinforcement Learning · Deep RL
Current LLM alignment techniques use pairwise human preferences at a sample level, and as such, they do not imply an alignment on the distributional level. We propose in this paper Alignment via Optimal Transport (AOT), a novel method for distributional preference alignment of LLMs. AOT aligns LLMs on unpaired preference data by making the reward distribution of the positive samples stochastically dominant in the first order on the distribution of negative samples. We introduce a convex relaxation of this first-order stochastic dominance and cast it as an optimal transport problem with a smooth and convex cost. Thanks to the one-dimensional nature of the resulting optimal transport problem and the convexity of the cost, it has a closed-form solution via sorting on empirical measures. We fine-tune LLMs with this AOT objective, which enables alignment by penalizing the violation of the stochastic dominance of the reward distribution of the positive samples on the reward distribution of the negative samples. We analyze the sample complexity of AOT by considering the dual of the OT problem and show that it converges at the parametric rate. Empirically, we show on a diverse set of alignment datasets and LLMs that AOT leads to state-of-the-art models in the 7B family of models when evaluated with Open LLM Benchmarks and AlpacaEval. Code for $\mathsf{AOT}$ is available in the Hugging Face TRL library \url{https://ibm.biz/AOT_TRL}.
Reinforcement Learning · Deep RL
In this paper, we present the e-COP algorithm, the first policy optimization algorithm for constrained Reinforcement Learning (RL) in episodic (finite horizon) settings. Such formulations are applicable when there are separate sets of optimization criteria and constraints on a system's behavior. We approach this problem by first establishing a policy difference lemma for the episodic setting, which provides the theoretical foundation for the algorithm. Then, we propose to combine a set of established and novel solution ideas to yield the e-COP algorithm that is easy to implement and numerically stable, and provide a theoretical guarantee on optimality under certain scaling assumptions. Through extensive empirical analysis using benchmarks in the Safety Gym suite, we show that our algorithm has similar or better performance than SoTA (non-episodic) algorithms adapted for the episodic setting. The scalability of the algorithm opens the door to its application in safety-constrained Reinforcement Learning from Human Feedback for Large Language or Diffusion Models.
Reinforcement Learning · Deep RL
Unsupervised skill discovery is a learning paradigm that aims to acquire diverse behaviors without explicit rewards. However, it faces challenges in learning complex behaviors and often leads to learning unsafe or undesirable behaviors. For instance, in various continuous control tasks, current unsupervised skill discovery methods succeed in learning basic locomotions like standing but struggle with learning more complex movements such as walking and running. Moreover, they may acquire unsafe behaviors like tripping and rolling or navigate to undesirable locations such as pitfalls or hazardous areas. In response, we present **DoDont** (Do’s and Dont’s), an instruction-based skill discovery algorithm composed of two stages. First, in instruction learning stage, DoDont leverages action-free instruction videos to train an instruction network to distinguish desirable transitions from undesirable ones. Then, in the skill learning stage, the instruction network adjusts the reward function of the skill discovery algorithm to weight the desired behaviors. Specifically, we integrate the instruction network into a distance-maximizing skill discovery algorithm, where the instruction network serves as the distance function. Empirically, with less than 8 instruction videos, DoDont effectively learns desirable behaviors and avoids undesirable ones across complex continuous control tasks. Code and videos are available at https://mynsng.github.io/dodont/
Reinforcement Learning · Deep RL
Efficiently solving unseen tasks remains a challenge in reinforcement learning (RL), especially for long-horizon tasks composed of multiple subtasks. Pre-training policies from task-agnostic datasets has emerged as a promising approach, yet existing methods still necessitate substantial interactions via RL to learn new tasks.We introduce MGPO, a method that leverages the power of Transformer-based policies to model sequences of goals, enabling efficient online adaptation through prompt optimization.In its pre-training phase, MGPO utilizes hindsight multi-goal relabeling and behavior cloning. This combination equips the policy to model diverse long-horizon behaviors that align with varying goal sequences.During online adaptation, the goal sequence, conceptualized as a prompt, is optimized to improve task performance. We adopt a multi-armed bandit framework for this process, enhancing prompt selection based on the returns from online trajectories.Our experiments across various environments demonstrate that MGPO holds substantial advantages in sample efficiency, online adaptation performance, robustness, and interpretability compared with existing methods.
Reinforcement Learning · Deep RL
In reinforcement learning (RL), it is common to apply techniques used broadly in machine learning such as neural network function approximators and momentum-based optimizers. However, such tools were largely developed for supervised learning rather than nonstationary RL, leading practitioners to adopt target networks, clipped policy updates, and other RL-specific implementation tricks to combat this mismatch, rather than directly adapting this toolchain for use in RL. In this paper, we take a different approach and instead address the effect of nonstationarity by adapting the widely used Adam optimiser. We first analyse the impact of nonstationary gradient magnitude --- such as that caused by a change in target network --- on Adam's update size, demonstrating that such a change can lead to large updates and hence sub-optimal performance.To address this, we introduce Adam-Rel.Rather than using the global timestep in the Adam update, Adam-Rel uses the *local* timestep within an epoch, essentially resetting Adam's timestep to 0 after target changes.We demonstrate that this avoids large updates and reduces to learning rate annealing in the absence of such increases in gradient magnitude. Evaluating Adam-Rel in both on-policy and off-policy RL, we demonstrate improved performance in both Atari and Craftax.We then show that increases in gradient norm occur in RL in practice, and examine the differences between our theoretical model and the observed data.
Reinforcement Learning · Deep RL
Computing Jacobians with automatic differentiation is ubiquitous in many scientific domains such as machine learning, computational fluid dynamics, robotics and finance. Even small savings in the number of computations or memory usage in Jacobian computations can already incur massive savings in energy consumption and runtime. While there exist many methods that allow for such savings, they generally trade computational efficiency for approximations of the exact Jacobian.In this paper, we present a novel method to optimize the number of necessary multiplications for Jacobian computation by leveraging deep reinforcement learning (RL) and a concept called cross-country elimination while still computing the exact Jacobian. Cross-country elimination is a framework for automatic differentiation that phrases Jacobian accumulation as ordered elimination of all vertices on the computational graph where every elimination incurs a certain computational cost.Finding the optimal elimination order that minimizes the number of necessary multiplications can be seen as a single player game which in our case is played by an RL agent.We demonstrate that this method achieves up to 33% improvements over state-of-the-art methods on several relevant tasks taken from relevant domains.Furthermore, we show that these theoretical gains translate into actual runtime improvements by providing a cross-country elimination interpreter in JAX that can execute the obtained elimination orders.